Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2678 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3478. Min Range: -8.3478
Max Act: 8.3478. Min Act: -0.1700
Data Index: 5897859 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3478. Min Range: -8.3478
Max Act: 8.1916. Min Act: -0.1700
Data Index: 2164998 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3478. Min Range: -8.3478
Max Act: 8.1603. Min Act: -0.1700
Data Index: 1308824 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3478. Min Range: -8.3478
Max Act: 8.1916. Min Act: -0.1700
Data Index: 4650784 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3478. Min Range: -8.3478
Max Act: 8.1291. Min Act: -0.1700
Data Index: 4507010 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3478. Min Range: -8.3478
Max Act: 8.0666. Min Act: -0.1700
Data Index: 5164825 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3478. Min Range: -8.3478
Max Act: 8.0041. Min Act: -0.1700
Data Index: 2653800 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3478. Min Range: -8.3478
Max Act: 7.9416. Min Act: -0.1700
Data Index: 7261337 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3478. Min Range: -8.3478
Max Act: 7.9728. Min Act: -0.1700
Data Index: 4533509 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3478. Min Range: -8.3478
Max Act: 7.9103. Min Act: -0.1700
Data Index: 1468291 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3478. Min Range: -8.3478
Max Act: 7.9103. Min Act: -0.1700
Data Index: 7174417 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3478. Min Range: -8.3478
Max Act: 7.8791. Min Act: -0.1700
Data Index: 650436 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3478. Min Range: -8.3478
Max Act: 7.8478. Min Act: -0.1700
Data Index: 6959774 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3478. Min Range: -8.3478
Max Act: 7.8791. Min Act: -0.1700
Data Index: 2503713 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3478. Min Range: -8.3478
Max Act: 7.8478. Min Act: -0.1700
Data Index: 6685696 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3478. Min Range: -8.3478
Max Act: 7.7853. Min Act: -0.1700
Data Index: 6634352 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3478. Min Range: -8.3478
Max Act: 7.7541. Min Act: -0.1700
Data Index: 2070700 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3478. Min Range: -8.3478
Max Act: 7.7228. Min Act: -0.1700
Data Index: 6942274 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3478. Min Range: -8.3478
Max Act: 7.7228. Min Act: -0.1700
Data Index: 4359253 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3478. Min Range: -8.3478
Max Act: 7.6916. Min Act: -0.1700
Data Index: 4119523 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19